Evaluation of AI for prostate cancer detection in biparametric-MRI screening population data
Question Does an AI system trained in a screening cohort perform as well as radiologists? Findings An AI trained on screening data achieved an AUROC of 0.83 (95% CI 0.73-0.92) with lower specificity at the same sensitivity levels as radiologists. Clinical relevance An AI system trained in a screening population has lower specificity than radiologists using PI-RADS v2.
Authors
- Stephan E. Maier (ORCID: https://orcid.org/0000-0003-0646-3893)
- Stefan Kuczera (ORCID: https://orcid.org/0000-0001-8684-8982)
- Jonas Wallström (ORCID: https://orcid.org/0000-0002-4453-6718)
- Fredrik Langkilde (ORCID: https://orcid.org/0000-0002-8706-4036)
- Magnus Gren
Institutions
- Brigham and Women's Hospital (US)
- Harvard University (US)
- Sahlgrenska University Hospital (SE)
- University of Gothenburg (SE)
Publication Details
- Journal
- European Radiology
- Published
- 2025-12-08
- DOI
- https://doi.org/10.1007/s00330-025-12198-5
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.65
Funders
- Cancerfonden
- Vetenskapsrådet
- Göteborgs Universitet
- Sahlgrenska Akademin